Task transitions in continual learning cause abrupt, width-persistent changes in the Neural Tangent Kernel of past data, a phenomenon the authors call reactivation, which is modulated by semantic novelty of the new classes.
Implicit regularization via neural feature alignment
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Reactivation: Empirical NTK Dynamics Under Task Shifts
Task transitions in continual learning cause abrupt, width-persistent changes in the Neural Tangent Kernel of past data, a phenomenon the authors call reactivation, which is modulated by semantic novelty of the new classes.